255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r2n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n81 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n81 - 2 device=2 binding=--interleave=4,5
|
|
OPENMPI detected
|
|
AcceleratorCudaInit[0]: ========================
|
|
AcceleratorCudaInit[0]: Device Number : 0
|
|
AcceleratorCudaInit[0]: ========================
|
|
AcceleratorCudaInit[0]: Device identifier: NVIDIA A100-SXM4-40GB
|
|
AcceleratorCudaInit[0]: totalGlobalMem: 42505273344
|
|
AcceleratorCudaInit[0]: managedMemory: 1
|
|
AcceleratorCudaInit[0]: isMultiGpuBoard: 0
|
|
AcceleratorCudaInit[0]: warpSize: 32
|
|
AcceleratorCudaInit[0]: pciBusID: 3
|
|
AcceleratorCudaInit[0]: pciDeviceID: 0
|
|
AcceleratorCudaInit[0]: maxGridSize (2147483647,65535,65535)
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit[0]: ========================
|
|
AcceleratorCudaInit[0]: Device Number : 0
|
|
AcceleratorCudaInit[0]: ========================
|
|
AcceleratorCudaInit[0]: Device identifier: NVIDIA A100-SXM4-40GB
|
|
AcceleratorCudaInit[0]: totalGlobalMem: 42505273344
|
|
AcceleratorCudaInit[0]: managedMemory: 1
|
|
AcceleratorCudaInit[0]: isMultiGpuBoard: 0
|
|
AcceleratorCudaInit[0]: warpSize: 32
|
|
AcceleratorCudaInit[0]: pciBusID: 3
|
|
AcceleratorCudaInit[0]: pciDeviceID: 0
|
|
AcceleratorCudaInit[0]: maxGridSize (2147483647,65535,65535)
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
OPENMPI detected
|
|
AcceleratorCudaInit: using default device
|
|
AcceleratorCudaInit: assume user either uses
|
|
AcceleratorCudaInit: a) IBM jsrun, or
|
|
AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding
|
|
AcceleratorCudaInit: Configure options --enable-setdevice=no
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 2 device 0 bus id: 0000:84:00.0
|
|
local rank 1 device 0 bus id: 0000:44:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 3 device 0 bus id: 0000:C4:00.0
|
|
SharedMemoryMpi: World communicator of size 32
|
|
SharedMemoryMpi: Node communicator of size 4
|
|
0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14f660000000 for comms buffers
|
|
Setting up IPC
|
|
|
|
__|__|__|__|__|__|__|__|__|__|__|__|__|__|__
|
|
__|__|__|__|__|__|__|__|__|__|__|__|__|__|__
|
|
__|_ | | | | | | | | | | | | _|__
|
|
__|_ _|__
|
|
__|_ GGGG RRRR III DDDD _|__
|
|
__|_ G R R I D D _|__
|
|
__|_ G R R I D D _|__
|
|
__|_ G GG RRRR I D D _|__
|
|
__|_ G G R R I D D _|__
|
|
__|_ GGGG R R III DDDD _|__
|
|
__|_ _|__
|
|
__|__|__|__|__|__|__|__|__|__|__|__|__|__|__
|
|
__|__|__|__|__|__|__|__|__|__|__|__|__|__|__
|
|
| | | | | | | | | | | | | |
|
|
|
|
|
|
Copyright (C) 2015 Peter Boyle, Azusa Yamaguchi, Guido Cossu, Antonin Portelli and other authors
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 2 of the License, or
|
|
(at your option) any later version.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
Current Grid git commit hash=188d2c7a4dc77807b545f5f2813cdb589b9e44ca: (HEAD -> develop, gh/develop, gh/HEAD) uncommited changes
|
|
|
|
Grid : Message : ================================================
|
|
Grid : Message : MPI is initialised and logging filters activated
|
|
Grid : Message : ================================================
|
|
Grid : Message : Requested 2147483648 byte stencil comms buffers
|
|
Grid : Message : MemoryManager Cache 34004218675 bytes
|
|
Grid : Message : MemoryManager::Init() setting up
|
|
Grid : Message : MemoryManager::Init() cache pool for recent allocations: SMALL 8 LARGE 2
|
|
Grid : Message : MemoryManager::Init() Non unified: Caching accelerator data in dedicated memory
|
|
Grid : Message : MemoryManager::Init() Using cudaMalloc
|
|
Grid : Message : 1.322217 s : Grid Layout
|
|
Grid : Message : 1.322221 s : Global lattice size : 48 48 48 48
|
|
Grid : Message : 1.322226 s : OpenMP threads : 4
|
|
Grid : Message : 1.322227 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.334654 s : Making s innermost grids
|
|
Grid : Message : 1.350732 s : Initialising 4d RNG
|
|
Grid : Message : 1.366586 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.366609 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 1.552812 s : Initialising 5d RNG
|
|
Grid : Message : 1.788072 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 1.788100 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 4.410228 s : Initialised RNGs
|
|
Grid : Message : 5.378304 s : Drawing gauge field
|
|
Grid : Message : 5.480955 s : Random gauge initialised
|
|
Grid : Message : 5.486330 s : Setting up Cshift based reference
|
|
Grid : Message : 10.493734 s : *****************************************************************
|
|
Grid : Message : 10.493756 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 10.493757 s : *****************************************************************
|
|
Grid : Message : 10.493758 s : *****************************************************************
|
|
Grid : Message : 10.493759 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 10.493760 s : * Vectorising space-time by 8
|
|
Grid : Message : 10.493761 s : * VComplexF size is 64 B
|
|
Grid : Message : 10.493762 s : * SINGLE precision
|
|
Grid : Message : 10.493763 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 10.493764 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 10.493765 s : *****************************************************************
|
|
Grid : Message : 11.322900 s : Called warmup
|
|
Grid : Message : 91.635298 s : Called Dw 30000 times in 8.06029e+07 us
|
|
Grid : Message : 91.635358 s : mflop/s = 4.17282e+07
|
|
Grid : Message : 91.635360 s : mflop/s per rank = 1.304e+06
|
|
Grid : Message : 91.635362 s : mflop/s per node = 5.21602e+06
|
|
Grid : Message : 91.635364 s : RF GiB/s (base 2) = 84790.6
|
|
Grid : Message : 91.635366 s : mem GiB/s (base 2) = 52994.1
|
|
Grid : Message : 91.635943 s : norm diff 1.05759e-13
|
|
Grid : Message : 91.645127 s : #### Dhop calls report
|
|
Grid : Message : 91.645134 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 91.645137 s : WilsonFermion5D TotalTime /Calls : 1344.72 us
|
|
Grid : Message : 91.645139 s : WilsonFermion5D CommTime /Calls : 919.516 us
|
|
Grid : Message : 91.645141 s : WilsonFermion5D FaceTime /Calls : 208.013 us
|
|
Grid : Message : 91.645143 s : WilsonFermion5D ComputeTime1/Calls : 2.91585 us
|
|
Grid : Message : 91.645145 s : WilsonFermion5D ComputeTime2/Calls : 230.62 us
|
|
Grid : Message : 91.645164 s : Average mflops/s per call : 1.77398e+10
|
|
Grid : Message : 91.645168 s : Average mflops/s per call per rank : 5.54368e+08
|
|
Grid : Message : 91.645170 s : Average mflops/s per call per node : 2.21747e+09
|
|
Grid : Message : 91.645172 s : Average mflops/s per call (full) : 4.24446e+07
|
|
Grid : Message : 91.645178 s : Average mflops/s per call per rank (full): 1.32639e+06
|
|
Grid : Message : 91.645181 s : Average mflops/s per call per node (full): 5.30557e+06
|
|
Grid : Message : 91.645183 s : WilsonFermion5D Stencil
|
|
Grid : Message : 91.645190 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 91.645191 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 91.645192 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 91.645194 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 91.645196 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 100.258410 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 100.258436 s : Called DwDag
|
|
Grid : Message : 100.258437 s : norm dag result 12.0422
|
|
Grid : Message : 100.264144 s : norm dag ref 12.0422
|
|
Grid : Message : 100.266954 s : norm dag diff 7.13141e-14
|
|
Grid : Message : 100.277106 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 100.339804 s : src_e0.499992
|
|
Grid : Message : 100.410472 s : src_o0.500008
|
|
Grid : Message : 100.427338 s : *********************************************************
|
|
Grid : Message : 100.427342 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 100.427343 s : * Vectorising space-time by 8
|
|
Grid : Message : 100.427345 s : * SINGLE precision
|
|
Grid : Message : 100.427352 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 100.427356 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 100.427357 s : *********************************************************
|
|
Grid : Message : 143.519100 s : Deo mflop/s = 3.95063e+07
|
|
Grid : Message : 143.522200 s : Deo mflop/s per rank 1.23457e+06
|
|
Grid : Message : 143.522400 s : Deo mflop/s per node 4.93829e+06
|
|
Grid : Message : 143.522700 s : #### Dhop calls report
|
|
Grid : Message : 143.522900 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 143.523100 s : WilsonFermion5D TotalTime /Calls : 1419.09 us
|
|
Grid : Message : 143.523300 s : WilsonFermion5D CommTime /Calls : 950.298 us
|
|
Grid : Message : 143.523500 s : WilsonFermion5D FaceTime /Calls : 264.253 us
|
|
Grid : Message : 143.523700 s : WilsonFermion5D ComputeTime1/Calls : 4.9827 us
|
|
Grid : Message : 143.523900 s : WilsonFermion5D ComputeTime2/Calls : 230.606 us
|
|
Grid : Message : 143.526000 s : Average mflops/s per call : 1.01623e+10
|
|
Grid : Message : 143.526400 s : Average mflops/s per call per rank : 3.17572e+08
|
|
Grid : Message : 143.526600 s : Average mflops/s per call per node : 1.27029e+09
|
|
Grid : Message : 143.526800 s : Average mflops/s per call (full) : 4.02201e+07
|
|
Grid : Message : 143.527100 s : Average mflops/s per call per rank (full): 1.25688e+06
|
|
Grid : Message : 143.527300 s : Average mflops/s per call per node (full): 5.02752e+06
|
|
Grid : Message : 143.527600 s : WilsonFermion5D Stencil
|
|
Grid : Message : 143.527700 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 143.527800 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 143.527900 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 143.528200 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 143.528300 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 143.245950 s : r_e6.02129
|
|
Grid : Message : 143.270360 s : r_o6.02097
|
|
Grid : Message : 143.282970 s : res12.0423
|
|
Grid : Message : 143.140976 s : norm diff 0
|
|
Grid : Message : 143.262015 s : norm diff even 0
|
|
Grid : Message : 143.325416 s : norm diff odd 0
|